Automatic classification of mice vocalizations using Machine Learning techniques and Convolutional Neural Networks
Fig 4
Confusion matrices related to the classification results obtained testing the proposed CNN for the three datasets.
On both axes there are the vocalization classes; in particular, the x axis refers to the predicted labels, while the y axis refers to the true ones. Notice that each row value is normalized with respect to the number of vocalizations of that row's class. The values in the range (0;1) can be interpreted as percentage values.